Demo: Gemma Scope: Sparse autoencoders on Gemma 2
5 464
32.5
Google Developers2.41 млн
Следующее
67 дней – 6 8367:02Популярные
111 дней – 8 9100:19
214 дней – 9 5510:09Опубликовано 18 октября 2024, 16:00
Sparse Autoencoders (SAEs) are an interpretability tool that allow you to inspect what concepts your LLM is thinking about. Learn more our open-source suite of SAEs on all layers of Gemma 2 2B and 9B, which enables everyone to analyze and steer Gemma's internals.
Watch more videos from Gemma Developer Day Tokyo → goo.gle/gemma-dev-tokyo
Subscribe to Google for Developers → goo.gle/developers
#Gemma #GemmaDeveloperDay
Products Mentioned: Gemma
Watch more videos from Gemma Developer Day Tokyo → goo.gle/gemma-dev-tokyo
Subscribe to Google for Developers → goo.gle/developers
#Gemma #GemmaDeveloperDay
Products Mentioned: Gemma
Свежие видео
4 дня – 451 0192:58:34
5 дней – 4456:26
9 дней – 1 432 6799:57
9 дней – 89 66814:44
11 дней – 81 7952:16
13 дней – 1 04829:31Случайные видео
226 дней – 1 479 84034:54
355 дней – 2 1498:03
09.07.23 – 142 29412:39
06.03.23 – 53 59526:02
13.02.21 – 83 8090:18
12.07.07 – 3 2002:41
13 дней – 1143:29
19 дней – 3590:17
19 дней – 5 4700:17
22 дня – 1 3860:41
23 дня – 35 0240:16
29 дней – 13 9820:24
7 часов – 5 60427:36